Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation
2026-06-02 • Information Retrieval
Information RetrievalArtificial Intelligence
AI summaryⓘ
The authors discuss how current graph foundation models struggle to adapt when the data changes because they rely on fixed knowledge. To fix this, they introduce a new method called HyRAG, which uses hyperbolic space to better represent tree-like external knowledge and retrieve relevant information. This approach helps the model understand both broad and detailed knowledge and combines it effectively for graph tasks. Their experiments show that this method improves model performance in situations where no prior training on the new data is done.
Graph Foundation ModelsRetrieval-Augmented GenerationHyperbolic SpaceKnowledge IndexingSemantic RetrievalDistribution ShiftZero-Shot LearningHubness PhenomenonGraph Representation LearningTree-Structured Data
Authors
Yifan Jin, Qirui Ji, Bin Qin, Jiangmeng Li, Lixiang Liu, Fuchun Sun, Changwen Zheng
Abstract
Graph foundation models (GFMs) emerged as a dominant paradigm in graph representation learning by leveraging large-scale pre-training for cross-domain inference. However, the parameterized knowledge encoded within these models is insufficient to cope with distribution shifts, limiting their generalization ability. To mitigate this issue, retrieval-augmented generation (RAG) has been introduced to incorporate external knowledge at inference time. Nevertheless, existing RAG frameworks operating in Euclidean space suffer from a fundamental geometric limitation: the polynomial volume growth of Euclidean space is inherently mismatched with the tree-structured external knowledge bases. This mismatch leads to the loss of semantic granularity in retrieval and gives rise to the hubness phenomenon.To address this limitation, we propose a Hyperbolic Retrieval-Augmented Generation (HyRAG) framework designed to enhance the generalization capabilities of GFMs. Specifically, the introduced Hyperbolic Knowledge Indexing module retains the tree-like hierarchies of the external knowledge base by modeling them within hyperbolic space. The Multi-granularity Retrieval module then provides GFMs with the global semantic anchors and local semantic nuances through coarse-grained and fine-grained knowledge retrieval, respectively. Finally, the Dual-path Fusion module achieves effective knowledge integration for graph tasks at both the feature and structural levels.Experiments on multiple graph benchmarks demonstrate significant improvements in the zero-shot setting, highlighting the generalization of our method for robust GFMs inference.